Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2213 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0680. Min Act: -0.0003

Data Index: 1276930 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0585. Min Act: -0.0003

Data Index: 366726 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0521. Min Act: -0.0003

Data Index: 947958 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0524. Min Act: -0.0003

Data Index: 397813 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0504. Min Act: -0.0003

Data Index: 367546 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0511. Min Act: -0.0003

Data Index: 398779 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0504. Min Act: -0.0003

Data Index: 1133143 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0522. Min Act: -0.0003

Data Index: 1030439 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0508. Min Act: -0.0003

Data Index: 1003470 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0402. Min Act: -0.0003

Data Index: 219122 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0485. Min Act: -0.0003

Data Index: 36763 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0436. Min Act: -0.0003

Data Index: 244785 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0463. Min Act: -0.0003

Data Index: 1087942 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0515. Min Act: -0.0003

Data Index: 94915 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0437. Min Act: -0.0003

Data Index: 1127432 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0485. Min Act: -0.0003

Data Index: 774456 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0469. Min Act: -0.0003

Data Index: 1022673 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0494. Min Act: -0.0003

Data Index: 154738 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0464. Min Act: -0.0003

Data Index: 675165 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0483. Min Act: -0.0003

Data Index: 911622 (C4 (Web Text))

Max Activating Token Index: 406